Learning Coordinated Bimanual Manipulation Policies using State Diffusion and Inverse Dynamics Models

• URL: http://arxiv.org/abs/2503.23271v1
• Date: Sun, 30 Mar 2025 01:25:35 GMT
• Title: Learning Coordinated Bimanual Manipulation Policies using State Diffusion and Inverse Dynamics Models
• Authors: Haonan Chen, Jiaming Xu, Lily Sheng, Tianchen Ji, Shuijing Liu, Yunzhu Li, Katherine Driggs-Campbell,
• Abstract summary: We infuse the predictive nature of human manipulation strategies into robot imitation learning.<n>We train a diffusion model to predict future states and compute robot actions that achieve the predicted states.<n>Our framework consistently outperforms state-of-the-art state-to-action mapping policies.
• Score: 22.826115023573205
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: When performing tasks like laundry, humans naturally coordinate both hands to manipulate objects and anticipate how their actions will change the state of the clothes. However, achieving such coordination in robotics remains challenging due to the need to model object movement, predict future states, and generate precise bimanual actions. In this work, we address these challenges by infusing the predictive nature of human manipulation strategies into robot imitation learning. Specifically, we disentangle task-related state transitions from agent-specific inverse dynamics modeling to enable effective bimanual coordination. Using a demonstration dataset, we train a diffusion model to predict future states given historical observations, envisioning how the scene evolves. Then, we use an inverse dynamics model to compute robot actions that achieve the predicted states. Our key insight is that modeling object movement can help learning policies for bimanual coordination manipulation tasks. Evaluating our framework across diverse simulation and real-world manipulation setups, including multimodal goal configurations, bimanual manipulation, deformable objects, and multi-object setups, we find that it consistently outperforms state-of-the-art state-to-action mapping policies. Our method demonstrates a remarkable capacity to navigate multimodal goal configurations and action distributions, maintain stability across different control modes, and synthesize a broader range of behaviors than those present in the demonstration dataset.

Related papers

• Action Flow Matching for Continual Robot Learning [57.698553219660376]
  Continual learning in robotics seeks systems that can constantly adapt to changing environments and tasks. We introduce a generative framework leveraging flow matching for online robot dynamics model alignment. We find that by transforming the actions themselves rather than exploring with a misaligned model, the robot collects informative data more efficiently.
  arXiv  Detail & Related papers  (2025-04-25T16:26:15Z)
• Embodied Chain of Action Reasoning with Multi-Modal Foundation Model for Humanoid Loco-manipulation [17.449836528972867]
  We introduce a novel framework that applies the embodied chain of action reasoning methodology to autonomously plan actions from textual instructions for humanoid loco-manipulation. Our method integrates humanoid-specific chain of thought methodology, including detailed affordance and body movement analysis, which provides a breakdown of the task into a sequence of locomotion and manipulation actions. We evaluate our method's efficacy on the decoupled upper and lower body control and demonstrate the effectiveness of the chain of robotic action reasoning strategies in comprehending human instructions.
  arXiv  Detail & Related papers  (2025-04-13T11:37:32Z)
• Planning-Guided Diffusion Policy Learning for Generalizable Contact-Rich Bimanual Manipulation [16.244250979166214]
  Generalizable Planning-Guided Diffusion Policy Learning (GLIDE) is an approach that learns to solve contact-rich bimanual manipulation tasks.<n>We propose a set of essential design options in feature extraction, task representation, action prediction, and data augmentation.<n>Our approach can enable a bimanual robotic system to effectively manipulate objects of diverse geometries, dimensions, and physical properties.
  arXiv  Detail & Related papers  (2024-12-03T18:51:39Z)
• Learning Goal-oriented Bimanual Dough Rolling Using Dynamic Heterogeneous Graph Based on Human Demonstration [19.74767906744719]
  Soft object manipulation poses significant challenges for robots, requiring effective techniques for state representation and manipulation policy learning. This research paper introduces a novel approach: a dynamic heterogeneous graph-based model for learning goal-oriented soft object manipulation policies.
  arXiv  Detail & Related papers  (2024-10-15T16:12:00Z)
• RoboPack: Learning Tactile-Informed Dynamics Models for Dense Packing [38.97168020979433]
  We introduce an approach that combines visual and tactile sensing for robotic manipulation by learning a neural, tactile-informed dynamics model. Our proposed framework, RoboPack, employs a recurrent graph neural network to estimate object states. We demonstrate our approach on a real robot equipped with a compliant Soft-Bubble tactile sensor on non-prehensile manipulation and dense packing tasks.
  arXiv  Detail & Related papers  (2024-07-01T16:08:37Z)
• Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation [65.46610405509338]
  We seek to learn a generalizable goal-conditioned policy that enables zero-shot robot manipulation. Our framework,Track2Act predicts tracks of how points in an image should move in future time-steps based on a goal. We show that this approach of combining scalably learned track prediction with a residual policy enables diverse generalizable robot manipulation.
  arXiv  Detail & Related papers  (2024-05-02T17:56:55Z)
• Transferring Foundation Models for Generalizable Robotic Manipulation [82.12754319808197]
  We propose a novel paradigm that effectively leverages language-reasoning segmentation mask generated by internet-scale foundation models.<n>Our approach can effectively and robustly perceive object pose and enable sample-efficient generalization learning.<n>Demos can be found in our submitted video, and more comprehensive ones can be found in link1 or link2.
  arXiv  Detail & Related papers  (2023-06-09T07:22:12Z)
• Model-Based Visual Planning with Self-Supervised Functional Distances [104.83979811803466]
  We present a self-supervised method for model-based visual goal reaching. Our approach learns entirely using offline, unlabeled data. We find that this approach substantially outperforms both model-free and model-based prior methods.
  arXiv  Detail & Related papers  (2020-12-30T23:59:09Z)
• CLOUD: Contrastive Learning of Unsupervised Dynamics [19.091886595825947]
  We propose to learn forward and inverse dynamics in a fully unsupervised manner via contrastive estimation. We demonstrate the efficacy of our approach across a variety of tasks including goal-directed planning and imitation from observations.
  arXiv  Detail & Related papers  (2020-10-23T15:42:57Z)
• Goal-Aware Prediction: Learning to Model What Matters [105.43098326577434]
  One of the fundamental challenges in using a learned forward dynamics model is the mismatch between the objective of the learned model and that of the downstream planner or policy. We propose to direct prediction towards task relevant information, enabling the model to be aware of the current task and encouraging it to only model relevant quantities of the state space. We find that our method more effectively models the relevant parts of the scene conditioned on the goal, and as a result outperforms standard task-agnostic dynamics models and model-free reinforcement learning.
  arXiv  Detail & Related papers  (2020-07-14T16:42:59Z)
• Learning Predictive Models From Observation and Interaction [137.77887825854768]
  Learning predictive models from interaction with the world allows an agent, such as a robot, to learn about how the world works. However, learning a model that captures the dynamics of complex skills represents a major challenge. We propose a method to augment the training set with observational data of other agents, such as humans.
  arXiv  Detail & Related papers  (2019-12-30T01:10:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.